{"id":"W4323266498","doi":"10.1142/s0219622023500360","title":"An Entity Extraction and Categorization Technique on Twitter Streams","year":2023,"lang":"en","type":"article","venue":"International Journal of Information Technology & Decision Making","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Word2vec; Information retrieval; Categorization; Social media; Entity linking; Task (project management); Information extraction; Process (computing); Semantic Web; Annotation; World Wide Web; Knowledge base; Data science; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006067427,0.001013784,0.0007392213,0.005578143,0.001492297,0.001152021,0.0008963327,0.000983327,0.003234813],"category_scores_gemma":[0.002038604,0.0002356269,0.001007141,0.004630705,0.0002103535,0.002559077,0.0009843436,0.0007818349,0.00313469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005154292,"about_ca_system_score_gemma":0.0007626899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006926324,"about_ca_topic_score_gemma":0.009668878,"domain_scores_codex":[0.9993174,0.00006834015,0.0000776013,0.000202937,0.0002204146,0.0001133479],"domain_scores_gemma":[0.9992206,0.0001674204,0.00006235572,0.0001077966,0.0003967491,0.00004506817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007929359,0.0003902001,0.01108755,0.0003459043,0.0001517139,0.001564159,0.0005474846,0.005921174,0.05174847,0.004891325,0.04010896,0.8824502],"study_design_scores_gemma":[0.0000946656,0.000321078,0.02712382,0.0001075996,0.0002519509,0.001777725,0.002336426,0.7335458,0.1221286,0.01274544,0.09939431,0.0001726057],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1763738,0.002076699,0.7696031,0.001613752,0.001134309,0.001406237,0.01795998,0.01388113,0.01595094],"genre_scores_gemma":[0.3865211,0.001332344,0.5531744,0.0003000436,0.0005673306,0.0006593878,0.03593928,0.0003700701,0.02113601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006926324,"threshold_uncertainty_score":0.01377201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01200378828492195,"score_gpt":0.328438379132472,"score_spread":0.3164345908475501,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}